2.765

2022影响因子

(CJCR)

  • 中文核心
  • EI
  • 中国科技核心
  • Scopus
  • CSCD
  • 英国科学文摘

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

二维解析张量投票算法研究

林洪彬 邵艳川 王伟

林洪彬, 邵艳川, 王伟. 二维解析张量投票算法研究. 自动化学报, 2016, 42(3): 472-480. doi: 10.16383/j.aas.2016.c150339
引用本文: 林洪彬, 邵艳川, 王伟. 二维解析张量投票算法研究. 自动化学报, 2016, 42(3): 472-480. doi: 10.16383/j.aas.2016.c150339
LIN Hong-Bin, SHAO Yan-Chuan, WANG Wei. The 2D Analytical Tensor Voting Algorithm. ACTA AUTOMATICA SINICA, 2016, 42(3): 472-480. doi: 10.16383/j.aas.2016.c150339
Citation: LIN Hong-Bin, SHAO Yan-Chuan, WANG Wei. The 2D Analytical Tensor Voting Algorithm. ACTA AUTOMATICA SINICA, 2016, 42(3): 472-480. doi: 10.16383/j.aas.2016.c150339

二维解析张量投票算法研究

doi: 10.16383/j.aas.2016.c150339
基金项目: 

河北省自然科学基金 E2012203002

国家自然科学基金 51305390

国家自然科学基金 61501394

详细信息
    作者简介:

    邵艳川 燕山大学电气工程学院硕士研究生.主要研究方向为点云处理.E-mail:15232332122@163.com

    王伟 燕山大学电气工程学院硕士研究生.主要研究方向为点云处理.E-mail:wangwei163email@163.com

    通讯作者:

    林洪彬 燕山大学电气工程学院副教授.主要研究方向为点云处理, 模式识别与计算机视觉.本文通信作者.E-mail:honphin@ysu.edu.cn

The 2D Analytical Tensor Voting Algorithm

Funds: 

Natural Science Foundation of Hebei Province E2012203002

National Natural Science Foundation of China 51305390

National Natural Science Foundation of China 61501394

More Information
    Author Bio:

    Master student at the School of Electrical Engineering, Yanshan University. His research interest covers point cloud data processing

    Master student at the School of Electrical Engineering, Yanshan University. His research interest covers point cloud data processing

    Corresponding author: LIN Hong-Bin Associate professor at the School of Electrical Engineering, Yanshan University. His research interest covers point cloud data processing, pattern recognition, and computer vision. Corresponding author of this paper
  • 摘要: 针对传统张量投票(Tensor voting)算法计算过程复杂、算法效率低的问题, 本文提出了一种二维解析张量投票算法.首先, 深入分析张量投票理论的基本思想, 分析传统张量投票算法的不足及其根源; 其次, 设计了一种二维解析棒张量投票新机制, 实现了二维解析棒张量投票的直接求取; 在此基础上, 利用二维解析棒张量投票不依赖参考坐标系的特性, 设计并求解了二维解析球张量投票表达式, 解决了长期困扰张量投票理论中球张量投票无法解析求解, 仅能通过迭代数值计算, 计算过程复杂、算法效率低、算法精度与算法效率存在矛盾的难题.最后, 通过仿真分析和对比实验验证了本文算法在精度和计算效率方面的性能均优于传统张量投票算法.
  • 图  1  传统张量投票算法流程

    Fig.  1  Flow-chart of traditional tensor voting algorithm

    图  2  二维张量投票示意图

    Fig.  2  Illustration of tensor voting in 2D

    图  3  标准棒张量投票示意图

    Fig.  3  Illustration of standard stick tensor voting

    图  4  传统张量投票中的衰减函数特性

    Fig.  4  Demonstration of decay function in traditional tensor voting

    图  5  任意两点间棒张量投票坐标变换示意图

    Fig.  5  Illustration of stick voting coordinate transformation between any two points

    图  6  由棒张量投票求取球张量投票

    Fig.  6  Ball tensor induced by stick tensor

    图  7  二维解析棒张量投票示意图

    Fig.  7  Illustration of stick voting analytical solution in 2D

    图  8  本文采用的衰减函数特性

    Fig.  8  Demonstration of adopted decay function

    图  9  棒张量T1形成的投票域

    Fig.  9  Voting filed generated by stick tensor T1

    图  10  棒张量T2形成的投票域

    Fig.  10  Voting filed generated by stick tensor T2

    图  11  球张量T3形成的投票域

    Fig.  11  Voting filed generated by ball tensor T3

    图  12  二维棒张量投票运行时间对比实验结果

    Fig.  12  Running time comparison between 2D stick tensor voting method

    图  13  二维球张量投票运行时间对比实验结果

    Fig.  13  Running time comparison between 2D ball tensor voting method

    图  14  两种张量投票算法结构推理效果

    Fig.  14  Results inferred by OTV and the proposed method

    图  15  本文算法用于灰度图像结构推理

    Fig.  15  Utilization of the proposed method in structure inference of gray scale image

    表  1  算法运行时间比较

    Table  1  Running time comparison between the methods

    投票 棒投票时间(ms) 球投票时间(ms)
    点数 传统方法 本文方法 传统方法 本文方法
    4 225 9.123 3.775 222.619 1.549
    6 241 11.820 6.137 292.801 2.273
    16 641 36.184 13.621 979.026 7.407
    下载: 导出CSV
  • [1] Guy G, Medioni G. Inference of surfaces, 3D curves, and junctions from sparse, noise, 3D data. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(11):1265-1277 doi: 10.1109/34.632985
    [2] Rashwan H A, Puig D, Garcia M A. Improving the robustness of variational optical flow through tensor voting. Computer Vision and Image Understanding, 2012, 116(9):953-966 doi: 10.1016/j.cviu.2012.04.006
    [3] Martinez-Sanchez A, Garcia I, Asano S, Lucic V, Fernandez J. Robust membrane detection based on tensor voting for electron tomography. Journal of Structural Biology, 2014, 186(1):49-61 doi: 10.1016/j.jsb.2014.02.015
    [4] Park M K, Lee S J, Jang I Y, Lee Y Y, Lee K H. Feature-aware filtering for point-set surface denoising. Computers and Graphics, 2013, 37(6):589-595 doi: 10.1016/j.cag.2013.05.004
    [5] Yi B, Liu Z Y, Tan J R, Cheng F B, Duan G F, Liu L G. Shape recognition of CAD models via iterative slippage analysis. Computer-Aided Design, 2014, 55:13-25 doi: 10.1016/j.cad.2014.04.008
    [6] Tang C K, Medioni G. Curvature-augmented tensor voting for shape inference from noisy 3D data. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(6):858-864 doi: 10.1109/TPAMI.2002.1008395
    [7] Tong W S, Tang C K, Mordohai P, Medioni G. First order augmentation to tensor voting for boundary inference and multiscale analysis in 3D. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(5):594-611 doi: 10.1109/TPAMI.2004.1273934
    [8] Tong W S, Tang C K, Medioni G. Epipolar geometry estimation for non-static scenes by 4D tensor voting. In:Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Kauai, USA:IEEE, 2001, 1:I-926-I-933
    [9] Mordohai P, Medioni G. Stereo using monocular cues within the tensor voting framework. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(6):968-982 doi: 10.1109/TPAMI.2006.129
    [10] Kim H S, Choi H K, Lee K H. Feature detection of triangular meshes based on tensor voting theory. Computer-Aided Design, 2009, 41(1):47-58 doi: 10.1016/j.cad.2008.12.003
    [11] Moreno R, Garcia M A, Puig D, Pizarro L, Burgeth B, Weickert J. On improving the efficiency of tensor voting. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(11):2215-2228 doi: 10.1109/TPAMI.2011.23
    [12] Wu T P, Yeung S K, Jia J, Tang C K, Medioni G. A closed-form solution to tensor voting:theory and applications. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(8):1482-1495 doi: 10.1109/TPAMI.2011.250
    [13] Maggiori E, Lotito P, Manterola H L, del Fresno M. Comments on "A closed-form solution to tensor voting:theory and applications". IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(12):2567-2568 doi: 10.1109/TPAMI.2014.2342233
    [14] Mordohai P, Medioni G. Tensor voting:a perceptual organization approach to computer vision and machine learning. Synthesis Lectures on Image, Video, and Multimedia Processing, 2006, 2(1):1-136 http://muriel.mycincylife.com/pdfread/tensor-voting-a-perceptual-organization-approach-to-computer-vision-and-machine-learning.pdf
  • 加载中
图(15) / 表(1)
计量
  • 文章访问数:  2221
  • HTML全文浏览量:  643
  • PDF下载量:  1021
  • 被引次数: 0
出版历程
  • 收稿日期:  2015-05-26
  • 录用日期:  2015-11-09
  • 刊出日期:  2016-03-01

目录

    /

    返回文章
    返回